most citedOn the Robustness of Monte Carlo Dropout Trained with Noisy Labels

3 citations · 7 across the 3 of their papers we have counts for

collaborators

5 papers

cs.LG20213 cited

On the Robustness of Monte Carlo Dropout Trained with Noisy Labels

Purvi Goel, Li Chen

The memorization effect of deep learning hinders its performance to effectively generalize on test set when learning with noisy labels. Prior study has discovered that epistemic un…

cs.LG2021

ICodeNet -- A Hierarchical Neural Network Approach for Source Code Author Identification

Pranali Bora, Tulika Awalgaonkar, Himanshu Palve +2

With the open-source revolution, source codes are now more easily accessible than ever. This has, however, made it easier for malicious users and institutions to copy the code with…

cs.CV20201 cited

Shape From Tracing: Towards Reconstructing 3D Object Geometry and SVBRDF Material from Images via Differentiable Path Tracing

Purvi Goel, Loudon Cohen, James Guesman +3

Reconstructing object geometry and material from multiple views typically requires optimization. Differentiable path tracing is an appealing framework as it can reproduce complex a…

cs.LG20203 cited

Robust Deep Learning with Active Noise Cancellation for Spatial Computing

Li Chen, David Yang, Purvi Goel +1

This paper proposes CANC, a Co-teaching Active Noise Cancellation method, applied in spatial computing to address deep learning trained with extreme noisy labels. Deep learning alg…

cs.IR2020

Deep Learning for Hindi Text Classification: A Comparison

Ramchandra Joshi, Purvi Goel, Raviraj Joshi

Natural Language Processing (NLP) and especially natural language text analysis have seen great advances in recent times. Usage of deep learning in text processing has revolutioniz…